Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 366 insertions, 0 deletions

diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c
new file mode 100644
index 000000000..baa9b14b1
--- /dev/null
+++ b/drivers/net/usb/cdc_eem.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * USB CDC EEM network interface driver
+ * Copyright (C) 2009 Oberthur Technologies
+ * by Omar Laazimani, Olivier Condemine
+ */
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ctype.h>
+#include <linux/ethtool.h>
+#include <linux/workqueue.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/crc32.h>
+#include <linux/usb/cdc.h>
+#include <linux/usb/usbnet.h>
+#include <linux/gfp.h>
+#include <linux/if_vlan.h>
+
+
+/*
+ * This driver is an implementation of the CDC "Ethernet Emulation
+ * Model" (EEM) specification, which encapsulates Ethernet frames
+ * for transport over USB using a simpler USB device model than the
+ * previous CDC "Ethernet Control Model" (ECM, or "CDC Ethernet").
+ *
+ * For details, see https://usb.org/sites/default/files/CDC_EEM10.pdf
+ *
+ * This version has been tested with GIGAntIC WuaoW SIM Smart Card on 2.6.24,
+ * 2.6.27 and 2.6.30rc2 kernel.
+ * It has also been validated on Openmoko Om 2008.12 (based on 2.6.24 kernel).
+ * build on 23-April-2009
+ */
+
+#define EEM_HEAD	2		/* 2 byte header */
+
+/*-------------------------------------------------------------------------*/
+
+static void eem_linkcmd_complete(struct urb *urb)
+{
+	dev_kfree_skb(urb->context);
+	usb_free_urb(urb);
+}
+
+static void eem_linkcmd(struct usbnet *dev, struct sk_buff *skb)
+{
+	struct urb		*urb;
+	int			status;
+
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb)
+		goto fail;
+
+	usb_fill_bulk_urb(urb, dev->udev, dev->out,
+			skb->data, skb->len, eem_linkcmd_complete, skb);
+
+	status = usb_submit_urb(urb, GFP_ATOMIC);
+	if (status) {
+		usb_free_urb(urb);
+fail:
+		dev_kfree_skb(skb);
+		netdev_warn(dev->net, "link cmd failure\n");
+		return;
+	}
+}
+
+static int eem_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	int status = 0;
+
+	status = usbnet_get_endpoints(dev, intf);
+	if (status < 0)
+		return status;
+
+	/* no jumbogram (16K) support for now */
+
+	dev->net->hard_header_len += EEM_HEAD + ETH_FCS_LEN + VLAN_HLEN;
+	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
+
+	return 0;
+}
+
+/*
+ * EEM permits packing multiple Ethernet frames into USB transfers
+ * (a "bundle"), but for TX we don't try to do that.
+ */
+static struct sk_buff *eem_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
+				       gfp_t flags)
+{
+	struct sk_buff	*skb2 = NULL;
+	u16		len = skb->len;
+	u32		crc = 0;
+	int		padlen = 0;
+
+	/* When ((len + EEM_HEAD + ETH_FCS_LEN) % dev->maxpacket) is
+	 * zero, stick two bytes of zero length EEM packet on the end.
+	 * Else the framework would add invalid single byte padding,
+	 * since it can't know whether ZLPs will be handled right by
+	 * all the relevant hardware and software.
+	 */
+	if (!((len + EEM_HEAD + ETH_FCS_LEN) % dev->maxpacket))
+		padlen += 2;
+
+	if (!skb_cloned(skb)) {
+		int	headroom = skb_headroom(skb);
+		int	tailroom = skb_tailroom(skb);
+
+		if ((tailroom >= ETH_FCS_LEN + padlen) &&
+		    (headroom >= EEM_HEAD))
+			goto done;
+
+		if ((headroom + tailroom)
+				> (EEM_HEAD + ETH_FCS_LEN + padlen)) {
+			skb->data = memmove(skb->head +
+					EEM_HEAD,
+					skb->data,
+					skb->len);
+			skb_set_tail_pointer(skb, len);
+			goto done;
+		}
+	}
+
+	skb2 = skb_copy_expand(skb, EEM_HEAD, ETH_FCS_LEN + padlen, flags);
+	dev_kfree_skb_any(skb);
+	if (!skb2)
+		return NULL;
+
+	skb = skb2;
+
+done:
+	/* we don't use the "no Ethernet CRC" option */
+	crc = crc32_le(~0, skb->data, skb->len);
+	crc = ~crc;
+
+	put_unaligned_le32(crc, skb_put(skb, 4));
+
+	/* EEM packet header format:
+	 * b0..13:	length of ethernet frame
+	 * b14:		bmCRC (1 == valid Ethernet CRC)
+	 * b15:		bmType (0 == data)
+	 */
+	len = skb->len;
+	put_unaligned_le16(BIT(14) | len, skb_push(skb, 2));
+
+	/* Bundle a zero length EEM packet if needed */
+	if (padlen)
+		put_unaligned_le16(0, skb_put(skb, 2));
+
+	return skb;
+}
+
+static int eem_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+	/*
+	 * Our task here is to strip off framing, leaving skb with one
+	 * data frame for the usbnet framework code to process.  But we
+	 * may have received multiple EEM payloads, or command payloads.
+	 * So we must process _everything_ as if it's a header, except
+	 * maybe the last data payload
+	 *
+	 * REVISIT the framework needs updating so that when we consume
+	 * all payloads (the last or only message was a command, or a
+	 * zero length EEM packet) that is not accounted as an rx_error.
+	 */
+	do {
+		struct sk_buff	*skb2 = NULL;
+		u16		header;
+		u16		len = 0;
+
+		/* incomplete EEM header? */
+		if (skb->len < EEM_HEAD)
+			return 0;
+
+		/*
+		 * EEM packet header format:
+		 * b0..14:	EEM type dependent (Data or Command)
+		 * b15:		bmType
+		 */
+		header = get_unaligned_le16(skb->data);
+		skb_pull(skb, EEM_HEAD);
+
+		/*
+		 * The bmType bit helps to denote when EEM
+		 * packet is data or command :
+		 *	bmType = 0	: EEM data payload
+		 *	bmType = 1	: EEM (link) command
+		 */
+		if (header & BIT(15)) {
+			u16	bmEEMCmd;
+
+			/*
+			 * EEM (link) command packet:
+			 * b0..10:	bmEEMCmdParam
+			 * b11..13:	bmEEMCmd
+			 * b14:		bmReserved (must be 0)
+			 * b15:		1 (EEM command)
+			 */
+			if (header & BIT(14)) {
+				netdev_dbg(dev->net, "reserved command %04x\n",
+					   header);
+				continue;
+			}
+
+			bmEEMCmd = (header >> 11) & 0x7;
+			switch (bmEEMCmd) {
+
+			/* Responding to echo requests is mandatory. */
+			case 0:		/* Echo command */
+				len = header & 0x7FF;
+
+				/* bogus command? */
+				if (skb->len < len)
+					return 0;
+
+				skb2 = skb_clone(skb, GFP_ATOMIC);
+				if (unlikely(!skb2))
+					goto next;
+				skb_trim(skb2, len);
+				put_unaligned_le16(BIT(15) | BIT(11) | len,
+						skb_push(skb2, 2));
+				eem_linkcmd(dev, skb2);
+				break;
+
+			/*
+			 * Host may choose to ignore hints.
+			 *  - suspend: peripheral ready to suspend
+			 *  - response: suggest N millisec polling
+			 *  - response complete: suggest N sec polling
+			 *
+			 * Suspend is reported and maybe heeded.
+			 */
+			case 2:		/* Suspend hint */
+				usbnet_device_suggests_idle(dev);
+				continue;
+			case 3:		/* Response hint */
+			case 4:		/* Response complete hint */
+				continue;
+
+			/*
+			 * Hosts should never receive host-to-peripheral
+			 * or reserved command codes; or responses to an
+			 * echo command we didn't send.
+			 */
+			case 1:		/* Echo response */
+			case 5:		/* Tickle */
+			default:	/* reserved */
+				netdev_warn(dev->net,
+					    "unexpected link command %d\n",
+					    bmEEMCmd);
+				continue;
+			}
+
+		} else {
+			u32	crc, crc2;
+			int	is_last;
+
+			/* zero length EEM packet? */
+			if (header == 0)
+				continue;
+
+			/*
+			 * EEM data packet header :
+			 * b0..13:	length of ethernet frame
+			 * b14:		bmCRC
+			 * b15:		0 (EEM data)
+			 */
+			len = header & 0x3FFF;
+
+			/* bogus EEM payload? */
+			if (skb->len < len)
+				return 0;
+
+			/* bogus ethernet frame? */
+			if (len < (ETH_HLEN + ETH_FCS_LEN))
+				goto next;
+
+			/*
+			 * Treat the last payload differently: framework
+			 * code expects our "fixup" to have stripped off
+			 * headers, so "skb" is a data packet (or error).
+			 * Else if it's not the last payload, keep "skb"
+			 * for further processing.
+			 */
+			is_last = (len == skb->len);
+			if (is_last)
+				skb2 = skb;
+			else {
+				skb2 = skb_clone(skb, GFP_ATOMIC);
+				if (unlikely(!skb2))
+					return 0;
+			}
+
+			/*
+			 * The bmCRC helps to denote when the CRC field in
+			 * the Ethernet frame contains a calculated CRC:
+			 *	bmCRC = 1	: CRC is calculated
+			 *	bmCRC = 0	: CRC = 0xDEADBEEF
+			 */
+			if (header & BIT(14)) {
+				crc = get_unaligned_le32(skb2->data
+						+ len - ETH_FCS_LEN);
+				crc2 = ~crc32_le(~0, skb2->data, skb2->len
+						- ETH_FCS_LEN);
+			} else {
+				crc = get_unaligned_be32(skb2->data
+						+ len - ETH_FCS_LEN);
+				crc2 = 0xdeadbeef;
+			}
+			skb_trim(skb2, len - ETH_FCS_LEN);
+
+			if (is_last)
+				return crc == crc2;
+
+			if (unlikely(crc != crc2)) {
+				dev->net->stats.rx_errors++;
+				dev_kfree_skb_any(skb2);
+			} else
+				usbnet_skb_return(dev, skb2);
+		}
+
+next:
+		skb_pull(skb, len);
+	} while (skb->len);
+
+	return 1;
+}
+
+static const struct driver_info eem_info = {
+	.description =	"CDC EEM Device",
+	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT,
+	.bind =		eem_bind,
+	.rx_fixup =	eem_rx_fixup,
+	.tx_fixup =	eem_tx_fixup,
+};
+
+/*-------------------------------------------------------------------------*/
+
+static const struct usb_device_id products[] = {
+{
+	USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_EEM,
+			USB_CDC_PROTO_EEM),
+	.driver_info = (unsigned long) &eem_info,
+},
+{
+	/* EMPTY == end of list */
+},
+};
+MODULE_DEVICE_TABLE(usb, products);
+
+static struct usb_driver eem_driver = {
+	.name =		"cdc_eem",
+	.id_table =	products,
+	.probe =	usbnet_probe,
+	.disconnect =	usbnet_disconnect,
+	.suspend =	usbnet_suspend,
+	.resume =	usbnet_resume,
+	.disable_hub_initiated_lpm = 1,
+};
+
+module_usb_driver(eem_driver);
+
+MODULE_AUTHOR("Omar Laazimani <omar.oberthur@gmail.com>");
+MODULE_DESCRIPTION("USB CDC EEM");
+MODULE_LICENSE("GPL");